Back to skill

Security audit

Autopilot Charter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning guide for deciding which recurring work to automate, and it does not install code, run commands, or request hidden access.

This appears safe to install as an advisory planning skill. Users should still review any later automation setup carefully, especially before giving agents access to inboxes, CRMs, analytics, or audience-facing publishing workflows.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says to use the skill when asked 'what to automate' or 'how to set up recurring AI runs,' which are broad phrases that could arise in many general workflow discussions. It does not provide narrow trigger phrases, exclusions, or negative examples to clarify when this skill should activate versus related automation-planning skills.

Content

No source excerpt is available for this finding.